Improved Transformer Model With Meteorological Constraints Enhances Time Series Prediction of Evapotranspiration in Arid Regions

Accurate estimation of evapotranspiration (ET) is crucial for effective water resources management and agricultural planning, particularly in arid and semi-arid regions. However, existing prediction approaches often suffer from limited generalization and systematic bias under complex climatic variability. This study proposes a novel iTransformer_ET framework that integrates improved temporal encoding and attention mechanisms to enhance ET time series prediction. The prediction model was optimized by combining a multi-source meteorological dataset covering the entire Arid Zone of Northwest China. Comprehensive evaluation against state-of-the-art statistical, machine learning, and deep learning models demonstrates that iTransformer_ET achieves the highest predictive accuracy, withR2=0.9562, RMSE = 0.3701 mm/day, MAPE = 24.35%, and an MDA of 1.0000. Notably, it yields the smallest bias magnitude (PBIAS = −13.07%), indicating minimal systematic deviation, and the highest explained variance score (EVS = 0.9819), confirming strong robustness and stability across varying ET ranges. The proposed approach offers a reliable and scalable solution for ET prediction, with potential applications in climate impact assessment, precision irrigation scheduling, and sustainable water resources management